Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3468 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.6306. Min Range: -4.6306

Max Act: 4.6306. Min Act: -0.0000

Data Index: 295235 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 4.6306. Min Range: -4.6306

Max Act: 4.4770. Min Act: -0.0000

Data Index: 427711 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 4.6306. Min Range: -4.6306

Max Act: 4.0563. Min Act: -0.0000

Data Index: 1093069 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 4.6306. Min Range: -4.6306

Max Act: 4.0990. Min Act: -0.0000

Data Index: 31228 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 4.6306. Min Range: -4.6306

Max Act: 4.1394. Min Act: -0.0000

Data Index: 588722 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 4.6306. Min Range: -4.6306

Max Act: 3.9731. Min Act: -0.0000

Data Index: 1096438 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 4.6306. Min Range: -4.6306

Max Act: 4.1354. Min Act: -0.0000

Data Index: 1274800 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 4.6306. Min Range: -4.6306

Max Act: 4.1267. Min Act: -0.0000

Data Index: 47410 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 4.6306. Min Range: -4.6306

Max Act: 4.1071. Min Act: -0.0000

Data Index: 977811 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 4.6306. Min Range: -4.6306

Max Act: 4.0835. Min Act: -0.0000

Data Index: 458780 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 4.6306. Min Range: -4.6306

Max Act: 4.0730. Min Act: -0.0000

Data Index: 603234 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 4.6306. Min Range: -4.6306

Max Act: 3.8578. Min Act: -0.0000

Data Index: 238519 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 4.6306. Min Range: -4.6306

Max Act: 3.7680. Min Act: -0.0000

Data Index: 1323858 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 4.6306. Min Range: -4.6306

Max Act: 4.0166. Min Act: -0.0000

Data Index: 807191 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 4.6306. Min Range: -4.6306

Max Act: 3.8480. Min Act: -0.0000

Data Index: 445935 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 4.6306. Min Range: -4.6306

Max Act: 3.7971. Min Act: -0.0000

Data Index: 1014139 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 4.6306. Min Range: -4.6306

Max Act: 3.7505. Min Act: -0.0000

Data Index: 794029 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 4.6306. Min Range: -4.6306

Max Act: 3.4565. Min Act: -0.0000

Data Index: 1300841 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 4.6306. Min Range: -4.6306

Max Act: 3.7415. Min Act: -0.0000

Data Index: 526867 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 4.6306. Min Range: -4.6306

Max Act: 3.7251. Min Act: -0.0000

Data Index: 601275 (C4 (Web Text))

Max Activating Token Index: 27